© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 6-RES-JB
    11. 222
    Prev
    Next
    INDEX
    Explanations

    time-related descriptions

    oai_token-act-pair · gpt-3.5-turbo

    references to duration and commitment in professional or personal contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iquid
    -0.56
    EEK
    -0.55
     CONTIN
    -0.55
     âĵĺ
    -0.54
    idth
    -0.53
    undrum
    -0.51
    currently
    -0.51
     complicate
    -0.51
    uku
    -0.50
    sites
    -0.50
    POSITIVE LOGITS
     last
    0.73
     earlier
    0.72
     ago
    0.64
     yesterday
    0.64
    addafi
    0.63
     beforehand
    0.60
     fateful
    0.60
    çİĭ
    0.60
     previous
    0.59
    terday
    0.58
    Activations Density 1.738%

    No Known Activations